Merge branch 'mlxsw-improvements'

Petr Machata says:

====================
mlxsw: Improvements

This patchset contains assortments of improvements to the mlxsw driver.
Please see individual patches for details.
====================

Link: https://patch.msgid.link/cover.1720447210.git.petrm@nvidia.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlxsw/core_thermal.c

@@ -100,6 +100,12 @@ static const struct mlxsw_cooling_states default_cooling_states[] = {
 
 struct mlxsw_thermal;
 
+struct mlxsw_thermal_cooling_device {
+	struct mlxsw_thermal *thermal;
+	struct thermal_cooling_device *cdev;
+	unsigned int idx;
+};
+
 struct mlxsw_thermal_module {
 	struct mlxsw_thermal *parent;
 	struct thermal_zone_device *tzdev;
@@ -123,7 +129,7 @@ struct mlxsw_thermal {
 	const struct mlxsw_bus_info *bus_info;
 	struct thermal_zone_device *tzdev;
 	int polling_delay;
-	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
+	struct mlxsw_thermal_cooling_device cdevs[MLXSW_MFCR_PWMS_MAX];
 	struct thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	struct mlxsw_cooling_states cooling_states[MLXSW_THERMAL_NUM_TRIPS];
 	struct mlxsw_thermal_area line_cards[];
@@ -147,7 +153,7 @@ static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal,
 	int i;
 
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
-		if (thermal->cdevs[i] == cdev)
+		if (thermal->cdevs[i].cdev == cdev)
 			return i;
 
 	/* Allow mlxsw thermal zone binding to an external cooling device */
@@ -352,17 +358,14 @@ static int mlxsw_thermal_get_cur_state(struct thermal_cooling_device *cdev,
 				       unsigned long *p_state)
 
 {
-	struct mlxsw_thermal *thermal = cdev->devdata;
+	struct mlxsw_thermal_cooling_device *mlxsw_cdev = cdev->devdata;
+	struct mlxsw_thermal *thermal = mlxsw_cdev->thermal;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int err, idx;
 	u8 duty;
+	int err;
 
-	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
-	if (idx < 0)
-		return idx;
-
-	mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0);
+	mlxsw_reg_mfsc_pack(mfsc_pl, mlxsw_cdev->idx, 0);
 	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
 		dev_err(dev, "Failed to query PWM duty\n");
@@ -378,22 +381,19 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev,
 				       unsigned long state)
 
 {
-	struct mlxsw_thermal *thermal = cdev->devdata;
+	struct mlxsw_thermal_cooling_device *mlxsw_cdev = cdev->devdata;
+	struct mlxsw_thermal *thermal = mlxsw_cdev->thermal;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int idx;
 	int err;
 
 	if (state > MLXSW_THERMAL_MAX_STATE)
 		return -EINVAL;
 
-	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
-	if (idx < 0)
-		return idx;
-
 	/* Normalize the state to the valid speed range. */
 	state = max_t(unsigned long, MLXSW_THERMAL_MIN_STATE, state);
-	mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state));
+	mlxsw_reg_mfsc_pack(mfsc_pl, mlxsw_cdev->idx,
+			    mlxsw_state_to_duty(state));
 	err = mlxsw_reg_write(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
 		dev_err(dev, "Failed to write PWM duty\n");
@@ -753,17 +753,21 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 	}
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) {
 		if (pwm_active & BIT(i)) {
+			struct mlxsw_thermal_cooling_device *mlxsw_cdev;
 			struct thermal_cooling_device *cdev;
 
+			mlxsw_cdev = &thermal->cdevs[i];
+			mlxsw_cdev->thermal = thermal;
+			mlxsw_cdev->idx = i;
 			cdev = thermal_cooling_device_register("mlxsw_fan",
-							       thermal,
+							       mlxsw_cdev,
 							       &mlxsw_cooling_ops);
 			if (IS_ERR(cdev)) {
 				err = PTR_ERR(cdev);
 				dev_err(dev, "Failed to register cooling device\n");
 				goto err_thermal_cooling_device_register;
 			}
-			thermal->cdevs[i] = cdev;
+			mlxsw_cdev->cdev = cdev;
 		}
 	}
 
@@ -824,8 +828,7 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 err_thermal_zone_device_register:
 err_thermal_cooling_device_register:
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
-		if (thermal->cdevs[i])
-			thermal_cooling_device_unregister(thermal->cdevs[i]);
+		thermal_cooling_device_unregister(thermal->cdevs[i].cdev);
 err_reg_write:
 err_reg_query:
 	kfree(thermal);
@@ -847,12 +850,8 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 		thermal->tzdev = NULL;
 	}
 
-	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) {
-		if (thermal->cdevs[i]) {
-			thermal_cooling_device_unregister(thermal->cdevs[i]);
-			thermal->cdevs[i] = NULL;
-		}
-	}
+	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
+		thermal_cooling_device_unregister(thermal->cdevs[i].cdev);
 
 	kfree(thermal);
 }

drivers/net/ethernet/mellanox/mlxsw/item.h

@@ -218,6 +218,10 @@ __mlxsw_item_bit_array_offset(const struct mlxsw_item *item,
 	}
 
 	max_index = (item->size.bytes << 3) / item->element_size - 1;
+	if (WARN_ONCE(index > max_index,
+		      "name=%s,index=%u,max_index=%u\n", item->name, index,
+		      max_index))
+		index = 0;
 	be_index = max_index - index;
 	offset = be_index * item->element_size >> 3;
 	in_byte_index  = index % (BITS_PER_BYTE / item->element_size);

drivers/net/ethernet/mellanox/mlxsw/pci.c

@@ -1784,6 +1784,7 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
 {
 	struct pci_dev *pdev = mlxsw_pci->pdev;
 	char mrsr_pl[MLXSW_REG_MRSR_LEN];
+	struct pci_dev *bridge;
 	int err;
 
 	if (!pci_reset_sbr_supported) {
@@ -1800,6 +1801,9 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
 sbr:
 	device_lock_assert(&pdev->dev);
 
+	bridge = pci_upstream_bridge(pdev);
+	if (bridge)
+		pci_cfg_access_lock(bridge);
 	pci_cfg_access_lock(pdev);
 	pci_save_state(pdev);
 
@@ -1809,6 +1813,8 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
 
 	pci_restore_state(pdev);
 	pci_cfg_access_unlock(pdev);
+	if (bridge)
+		pci_cfg_access_unlock(bridge);
 
 	return err;
 }